Add note context visibility in chat and standardize UI design tokens

Improve chat context: build_context() now returns metadata about auto-found
notes, emitted as an SSE event so the frontend can display context pills
showing which notes influenced the response. Users can promote notes for
deeper context (+) or exclude irrelevant ones (x). A note picker lets users
manually attach notes. Multi-word search uses per-term AND matching, and
auto-search iterates keywords individually for broader OR-style coverage.

Standardize styling: introduce CSS design tokens (--radius-sm/md/lg/pill,
--color-success/warning/overlay, --focus-ring) and migrate all components
to use them. Fix header alignment to full-width, add active nav link state,
replace hardcoded colors with CSS variables, and normalize button padding.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/fabledassistant/routes/chat.py

@@ -85,6 +85,7 @@ async def send_message_route(conv_id: int):
     if not content:
         return jsonify({"error": "content is required"}), 400
     context_note_id = data.get("context_note_id")
+    exclude_note_ids = data.get("exclude_note_ids") or []
 
     # Save user message
     await add_message(conv_id, "user", content, context_note_id=context_note_id)
@@ -96,11 +97,17 @@ async def send_message_route(conv_id: int):
             history.append({"role": msg.role, "content": msg.content})
 
     # Build context with note search, URL fetching, etc.
-    messages = await build_context(history, context_note_id, content)
+    messages, context_meta = await build_context(
+        history, context_note_id, content, exclude_note_ids=exclude_note_ids
+    )
 
     model = conv.model or await get_setting("default_model", Config.OLLAMA_MODEL)
 
     async def generate():
+        # Emit context metadata before streaming LLM response
+        context_event = json.dumps({"context": context_meta})
+        yield f"data: {context_event}\n\n"
+
         full_response = []
         try:
             async for chunk in stream_chat(messages, model):